Files
dev-puppeteer/my-deepagent/docs/schemas/workflows/code-investigation@1.yaml
chungyeong 17ba5d723b feat(my-deepagent): v0.1.0 Step 0~5 — scaffolding through deepagent + OpenRouter
Python rewrite of the agent harness on top of deepagents 0.6.1 + langchain 1.x,
replacing the abandoned TS attempt in packages/. 388 unit/integration tests pass.

Steps
-----
0. Scaffolding — uv workspace, ruff/mypy/pre-commit/alembic, src/tests/docs
   trees with docs/schemas/ seeded from my-deepagent-seed/.
1. Core — config (pydantic-settings with MYDEEPAGENT_ env prefix and TOML
   source), enums (Backend, Capability, RiskLevel, ApprovalDecisionAction,
   ApprovalState, RunState, RunPhaseState, SessionState, ErrorClass),
   errors (MyDeepAgentError + BudgetExhaustedError with PEP-3134 cause +
   context suppression), hash (canonical JSON + sha256).
2. Persona/Workflow/Binding — pydantic v2 schemas with tuple-based deep
   immutability (post-construction hash drift prevented), YAML loaders,
   deterministic auto-select (preferred_backends → version → name → hash),
   override resolution with ineligibility diagnostics, PersonaConsentStore
   with fcntl.flock + tmp+fsync+rename atomic write.
3. Artifact schema registry — Draft202012Validator, multi-root resolution,
   structured ValidationFinding output.
4. Persistence — 18 SQLAlchemy 2.0 async ORM models with FK CASCADE/RESTRICT,
   WAL + busy_timeout + foreign_keys PRAGMA, alembic baseline +
   ux_active_run_repo_base partial unique index, LangGraph SqliteSaver as
   context manager only (lifecycle safety).
5. DeepAgent session — build_agent wires Persona → create_deep_agent with
   LocalShellBackend / FilesystemBackend / StateBackend / CompositeBackend,
   ChatOpenAI(base_url=openrouter) for openrouter: model strings, and 4
   middleware classes (cost / audit-tool / safety-shell / fallback-model).

Critical workarounds
--------------------
- deepagents 0.6.1 rejects FilesystemPermission together with backends that
  implement SandboxBackendProtocol (LocalShellBackend). SafetyShellMiddleware
  enforces destructive-command and secret-path policy at the tool layer
  instead, and build_agent strips the permissions kwarg when the persona's
  deepagents_backend is local_shell.
- FilesystemOperation in deepagents is Literal['read', 'write'] only;
  _map_operations collapses our richer schema (read/write/edit/ls) safely.

Real OpenRouter smoke
---------------------
test_openrouter_deepagents_local_shell_smoke calls DeepSeek via deepagents +
LocalShellBackend + SafetyShellMiddleware end-to-end. PASS, ~$0.000001 cost,
input=9 / output=1 tokens with content "OK".

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-15 19:40:02 +09:00

64 lines
2.2 KiB
YAML

name: code-investigation
version: 1
description: "코드베이스 탐색 → 요약 보고서 생성. 구조 파악·의존성 분석·이슈 발굴."
roles:
- id: explorer
required_capabilities:
- evidence_check
- code_review
preferred_backends:
- openrouter
fallback_personas:
- "openrouter-claude-code-reviewer@1"
- "openrouter-deepseek-verifier@1"
- id: summarizer
required_capabilities:
- evidence_check
- final_report_compose
preferred_backends:
- openrouter
fallback_personas:
- "openrouter-claude-spec-writer@1"
phases:
- key: explore
title: "코드베이스 탐색 및 정보 수집"
risk: low
role: explorer
expected_artifact:
path: artifacts/exploration.json
schema: dev/spec@1
gates: []
timeout_seconds: 600
instructions: |
코드베이스를 체계적으로 탐색합니다.
glob으로 전체 파일 구조를 파악하고 read_file로 핵심 파일을 읽습니다.
grep으로 주요 패턴·의존성·진입점을 검색합니다.
발견한 내용 (구조, 주요 컴포넌트, 의존성, 잠재적 이슈)을
dev/spec@1 형식으로 artifacts/exploration.json에 write_file로 저장합니다.
requirements 필드: 탐색 목적
approach 필드: 탐색한 파일 목록 및 방법
acceptance_criteria 필드: 발견한 핵심 사실들
risks 필드: 발견한 잠재적 이슈들
max_budget_usd: 0.50
- key: summarize
title: "탐색 결과 최종 보고서 작성"
risk: low
role: summarizer
expected_artifact:
path: artifacts/report.json
schema: common/final-report@1
gates:
- report_approved
timeout_seconds: 300
instructions: |
artifacts/exploration.json을 read_file로 읽고 common/final-report@1 형식으로
최종 보고서를 작성합니다.
status: "completed"
phases: explore와 summarize 단계 정보
findings: exploration.json의 risks 항목을 finding으로 변환
artifacts: exploration.json 경로 포함
보고서를 write_file로 artifacts/report.json에 저장합니다.
max_budget_usd: 0.30
default_gates: []
max_total_budget_usd: 1.0